AI 导读
我没想到事情会这样发展，但我认为对大多数集成来说，MCP 比 CLI 更好。 模型在工具调用方面已经强了很多，我们可以延迟加载工具，而且 MCP 现在是无状态的。 如果你需要组合/过滤数据，给你的 MCP 工具加上 query 之类的参数。
正文
I was not expecting things to go this way, but I think MCPs are better than CLIs for most integrations.
The models have gotten much better at tool calling, we can defer tools & MCP is now stateless.
If you need to compose/filter data, add params like query to your MCP tools.
来源：@trq212 · x.com